© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7440
    Prev
    Next
    INDEX
    Explanations

    jet engine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    THEY
    -1.60
     Bibl
    -1.52
    fortunately
    -1.52
    
    -1.45
     PREFACE
    -1.45
     Ukraina
    -1.44
     LYON
    -1.41
    뚤
    -1.41
    癭
    -1.39
    yesterday
    -1.36
    POSITIVE LOGITS
    When
    1.63
     weirdly
    1.52
    Before
    1.50
    In
    1.48
     to
    1.42
     здесь
    1.40
     Leuten
    1.39
     unwind
    1.37
     Rechten
    1.37
     When
    1.36
    Activations Density 0.025%

    No Known Activations